Oxford Handbook of Applied Nonparametric and Semiparametric Econometrics and Statistics (eBook)

This volume, edited by Jeffrey Racine, Liangjun Su, and Aman Ullah, contains the latest research on nonparametric and semiparametric econometrics and statistics. These data-driven models seek to replace the classical parametric models of the past, which were rigid and often linear. Chapters by leading international econometricians and statisticians highlight the interface between econometrics and statistical methods for nonparametric and semiparametric procedures. They provide a balanced view of new developments in the modeling of cross-section, time series, panel, and spatial data. Topics of the volume include: the methodology of semiparametric models and special regressor methods; inverse, ill-posed, and well-posed problems; methodologies related to additive models; sieve regression, nonparametric and semiparametric regression, and the true error of competing approximate models; support vector machines and their modeling of default probability; series estimation of stochastic processes and their application in Econometrics; identification, estimation, and specification problems in semilinear time series models; nonparametric and semiparametric techniques applied to nonstationary or near nonstationary variables; the estimation of a set of regression equations; and a new approach to the analysis of nonparametric models with exogenous treatment assignment.